Rippling had a writeup on this. 40% of R&D payroll going to tokens, one engineer
at $50k/month. They got it down 37% just by routing cheap stuff to cheap models,
no usage cut.
DeepSeek costs OpenCode Go user $1.14/day; dual DGX breaks even in 24 years
51–60 of 67 posts
Re: DeepSeek costs OpenCode Go user $1.14/day; dual DGX breaks even in 24 years
#52It is worth mentioning DGX is about a third up to a half performance of a 6 year GPU Rtx3090...
I prefer to stay with my 3090s.
Re: DeepSeek costs OpenCode Go user $1.14/day; dual DGX breaks even in 24 years
#53Appreciate the heads-up. Even if some of this is overblown, the transparency thing is a legit concern. Gonna double-check my config before I touch OpenCode again
Re: DeepSeek costs OpenCode Go user $1.14/day; dual DGX breaks even in 24 years
#54Earlier quoted context omitted.
agreed. when using local models, they did send your prompts to openai with 30 day retention to make the titles, silently. their recent changes to the privacy policy broke their promise of zero data retention. specifically, they offered chatgpt luna under a zero data retention privacy policy. luna was later shown to be 30 days retention. their privacy policy has never guaranteed your prompts will not be logged and whe…
Plus 100 to this. Of all the harnesses I find it to be the worst. IMO training should always require opt in and the way they continue to run their business/framework is shady.
What harnesses do you favor? Any good contender apart frompi or Hermes?
Re: DeepSeek costs OpenCode Go user $1.14/day; dual DGX breaks even in 24 years
#55Fellow readers, would anyone please mind sharing their current experiences? qwen3.6-35b-a3b for local inference, GitHub Copilot Chat was previously worth it, and no longer is, tried OpenRouter and still read through their rankings to see what the industry is actively using, wholesale migrated to OpenCode Zen/Go. Does this mirror what other people have been experiencing in waves?
I've been using Qwen3.6 models locally for a couple of weeks. Both the A3B moe and the dense variant. The moe works well in Librechat combined with my local search/Web retrieval system. All components use open source projects such as SearXNG, Crawl4AI, MetaMCP, Jina rerank, but all needed quite a bit of coding to work nicely together.
I get 140 tok/s on short prompts on an rtx3090 on the qwen3.6 moe which makes is easily 4x the speed of Chatgpt or Claude doing Web research.
But it is a much simpler model. It is only good for simple queries, usually I search for cheapest product in stock in my country available online and stuff like that.
I use the dense model for planning and such, but on its own it is much inferior to for example opus. It needs careful pipelines that check facts and such and in such harness it can be used for mamy tasks.
Re: DeepSeek costs OpenCode Go user $1.14/day; dual DGX breaks even in 24 years
#56Earlier quoted context omitted.
One thing I realized is just how much offline local models can hurt mass data collection. For example, I needed to write an invitation letter for immigration control for a relative visiting me. Previously I would have used a search engine for a template. Today I fire up my local qwen 3.5-9b for this kind of stuff and feed it all the private data I need. Unfortunately it is unlikely the average user will known how to…
I hope for local model chat inexperienced users are just using llama.cpp's built-in web server interface, which gives you everything you need. No need for a harness or any other chat client.
I have tried running llamma.cpp on my PC and I found it hard getting it to run at decent speed. On Qwen 3.5-9b I get at most 10tk/s.
I eventually switched to LM studio and the same model runs much better, like 70tk/s.
Not sure if it was because I was running llama.cpp inside podman or badly tuned LLM arguments. But LM studio is unfortunately much more practical.
Although I agree with you. I do not really know what kind of telemetry LM studio is running and I would rather not be using it.
Re: DeepSeek costs OpenCode Go user $1.14/day; dual DGX breaks even in 24 years
#57Beware of the author of tweet, who happens to be author of OpenCode - OpenCode will leak all your data to themselves and to shady 3rd parties. Author feigned ignorance and never fixed the issue. OpenCode among other harnesses is the shadiest of all. https://github.com/anomalyco/opencode/issues/10416
Reading this issue was enough for me to never ever consider OpenCode: https://github.com/anomalyco/opencode/issues/6355
Re: DeepSeek costs OpenCode Go user $1.14/day; dual DGX breaks even in 24 years
#58Earlier quoted context omitted.
Plus 100 to this. Of all the harnesses I find it to be the worst. IMO training should always require opt in and the way they continue to run their business/framework is shady.
What harnesses do you favor? Any good contender apart frompi or Hermes?
I still use Pi a lot but have built a lot on top of it. My big thing is I have found a lot of use in having sub agents so I took preexisting work and further customized.
Re: DeepSeek costs OpenCode Go user $1.14/day; dual DGX breaks even in 24 years
#59The reason to run local models is not for coding mostly it's for learning how to deploy models and tinker with self hosting. It's also for massively crunching data 24/7. Imaging having an agent analyzing constinous log streams etc .. that could be a usescse where even deepseek could add up cost.
Privacy, no need to pay for tokens, offline usage, endless possibilities - you do not have to pay for tokens (subscribtion payment), so you can do more. The big issue is that local models are not "ready yet" compared to frontier and paid services. It is hard to run decent model without decent hardware. And to be honest even if you can buy hq hardware and spend a lot of money then it is not the same quality.
Re: DeepSeek costs OpenCode Go user $1.14/day; dual DGX breaks even in 24 years
#60It is worth mentioning DGX is about a third up to a half performance of a 6 year GPU Rtx3090... I prefer to stay with my 3090s.
The 3090s also don't have enough VRAM to run larger models too. It really comes down to how you like to develop (synchronously with lots of steering vs async agentic)